commit f0845a482d908540259276240a7551b4025cd1e7 Author: ModelHub XC Date: Sat Jun 13 01:38:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/business-advisor-llama-3b-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4858e90 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +business-advisor-llama-3b-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b6fb52 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: HSB786/business-advisor-llama-3b-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/HSB786/business-advisor-llama-3b-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#business-advisor-llama-3b-v2-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/business-advisor-llama-3b-v2-GGUF/resolve/main/business-advisor-llama-3b-v2.f16.gguf) | f16 | 6.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/business-advisor-llama-3b-v2.IQ4_XS.gguf b/business-advisor-llama-3b-v2.IQ4_XS.gguf new file mode 100644 index 0000000..89a0e0b --- /dev/null +++ b/business-advisor-llama-3b-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dae193cc5031a4dd119857afd356bc768855c1fce452e49e488df62f6b27bb1 +size 1840908096 diff --git a/business-advisor-llama-3b-v2.Q2_K.gguf b/business-advisor-llama-3b-v2.Q2_K.gguf new file mode 100644 index 0000000..61da2e8 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c010882ca423791d27f23af2a9466b2b4a3967c85ca33852a7bb2fc8195cae6a +size 1363937088 diff --git a/business-advisor-llama-3b-v2.Q3_K_L.gguf b/business-advisor-llama-3b-v2.Q3_K_L.gguf new file mode 100644 index 0000000..9b23f92 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7b3b67abaa0bb48a912f1abb6f4b91a4a3e0b4b1b9816b5750c1843b8985b1 +size 1815349056 diff --git a/business-advisor-llama-3b-v2.Q3_K_M.gguf b/business-advisor-llama-3b-v2.Q3_K_M.gguf new file mode 100644 index 0000000..2ef9e21 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a53d2f39720345847dc37cf102972542c537750e849a13c42bdb00a79e34b3e +size 1687160640 diff --git a/business-advisor-llama-3b-v2.Q3_K_S.gguf b/business-advisor-llama-3b-v2.Q3_K_S.gguf new file mode 100644 index 0000000..f3e92fd --- /dev/null +++ b/business-advisor-llama-3b-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ccc43da083603e2fd1ed0dfba172cf52ae37778a5b30cd59ae8e872d4d0124 +size 1542850368 diff --git a/business-advisor-llama-3b-v2.Q4_K_M.gguf b/business-advisor-llama-3b-v2.Q4_K_M.gguf new file mode 100644 index 0000000..0ba0915 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df45300ba84bf6c43f688102bc3a76a30bc029057aa6af86ebc3cbe13e365164 +size 2019379008 diff --git a/business-advisor-llama-3b-v2.Q4_K_S.gguf b/business-advisor-llama-3b-v2.Q4_K_S.gguf new file mode 100644 index 0000000..9710f05 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf346c83a9cfb2137eced30910bbccc8cb97e373358eb40196af6bca00c9ef07 +size 1928202048 diff --git a/business-advisor-llama-3b-v2.Q5_K_M.gguf b/business-advisor-llama-3b-v2.Q5_K_M.gguf new file mode 100644 index 0000000..d247c0a --- /dev/null +++ b/business-advisor-llama-3b-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c4a6b5841f5f7b6e3c5484bfdf55c6d128a10a8bd8f27195ac7f9236f523b7 +size 2322155328 diff --git a/business-advisor-llama-3b-v2.Q5_K_S.gguf b/business-advisor-llama-3b-v2.Q5_K_S.gguf new file mode 100644 index 0000000..ffa7084 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9378aff6ef30c8ef8a191926b9e558e5ce01cfc45861b85377f9c773e3e75e26 +size 2269513536 diff --git a/business-advisor-llama-3b-v2.Q6_K.gguf b/business-advisor-llama-3b-v2.Q6_K.gguf new file mode 100644 index 0000000..c2f2fe7 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1744eb7ff53ed4548551b16429a940dfe3dd673d0aec6ab1115c604a01c83523 +size 2643855168 diff --git a/business-advisor-llama-3b-v2.Q8_0.gguf b/business-advisor-llama-3b-v2.Q8_0.gguf new file mode 100644 index 0000000..28165c5 --- /dev/null +++ b/business-advisor-llama-3b-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92dad065dff9376be0194b5b9a8219bd5ef021be5de058295cf64687bad8aef3 +size 3421900608 diff --git a/business-advisor-llama-3b-v2.f16.gguf b/business-advisor-llama-3b-v2.f16.gguf new file mode 100644 index 0000000..2d291ef --- /dev/null +++ b/business-advisor-llama-3b-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:274409060e9dd2993df96b72df091446d16b7c2f5fbf35e4715bce89e5aafee9 +size 6433689408